Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 2740
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    68
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    product or service descriptions highlighting features, options, or offerings.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @trainjumperx

    phrases related to features and options, especially in a product or service context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.53
     Audiodateien
    -0.47
    HttpFoundation
    -0.46
    sistors
    -0.41
     ویکی‌پدیای
    -0.40
    gemeen
    -0.39
    )==
    -0.38
     Мексичка
    -0.38
     belangrijkste
    -0.36
     meisten
    -0.36
    POSITIVE LOGITS
     choices
    0.59
     options
    0.57
     CreateTagHelper
    0.50
    choices
    0.48
    styleable
    0.47
    ValueStyle
    0.47
     choice
    0.46
     option
    0.45
     Options
    0.45
    styleUrls
    0.44
    Activations Density 0.063%

    No Known Activations